2023-09-26 10:50:46 +02:00
{
"cells": [
{
"cell_type": "code",
"execution_count": 7,
"id": "3a96a25b-b38a-4485-b7ff-2509236757cb",
"metadata": {},
"outputs": [],
"source": [
"from pathlib import Path\n",
"import pandas as pd\n",
"import os\n",
"import matplotlib.pyplot as plt\n",
"import obspy\n",
"from obspy.core.event import read_events\n",
"\n",
"import seisbench\n",
"import seisbench.data as sbd\n",
"import seisbench.util as sbu\n",
"import numpy as np\n",
2023-10-12 14:27:53 +02:00
"\n"
2023-09-26 10:50:46 +02:00
]
},
{
"cell_type": "markdown",
"id": "b8d8aeaf-56e7-4bb0-9e3d-a41f2197d0f4",
"metadata": {},
"source": [
"# Creating a dataset"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "53e5a331-6b24-4da7-a0ba-7931a9d79dd0",
"metadata": {},
"outputs": [],
"source": [
"input_path = \"/net/pr2/projects/plgrid/plggeposai/datasets/bogdanka\"\n",
"catalog_path = \"/net/pr2/projects/plgrid/plggeposai/datasets/bogdanka/BOIS_all.xml\"\n",
"output_path = \"/net/pr2/projects/plgrid/plggeposai/kmilian/platform-demo-scripts/datasets/bogdanka/seisbench_format\"\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "426d4428-2bfa-492a-93d0-01c143d77ddc",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/net/pr2/projects/plgrid/plggeposai/mambaforge/envs/eposai/lib/python3.11/site-packages/obspy/io/quakeml/core.py:193: UserWarning: Setting attribute \"preferred_description\" failed. Value \"uncertainty elipse\" could not be converted to type \"Enum([\"horizontal uncertainty\", \"uncertainty ellipse\", \"confidence ellipsoid\"])\". The attribute \"preferred_description\" will not be set and will be missing in the resulting object.\n",
" warnings.warn(msg)\n"
]
}
],
"source": [
"events = read_events(catalog_path)"
]
},
{
"cell_type": "markdown",
"id": "281a13f7-d8d9-4d6c-a97c-89b1044671ad",
"metadata": {},
"source": [
"### Define train/dev/test split"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "28f666f4-16c8-446f-9428-d28d9ce6f8f2",
"metadata": {},
"outputs": [],
"source": [
"def get_event_params(event): \n",
"\n",
" \n",
" origin = event.preferred_origin()\n",
" if origin is None:\n",
" return {}\n",
"\n",
" mag = event.preferred_magnitude()\n",
"\n",
" source_id = str(event.resource_id)\n",
"\n",
" event_params = {\n",
" \"source_id\": source_id,\n",
" \"source_origin_uncertainty_sec\": origin.time_errors[\"uncertainty\"],\n",
" \"source_latitude_deg\": origin.latitude,\n",
" \"source_latitude_uncertainty_km\": origin.latitude_errors[\"uncertainty\"],\n",
" \"source_longitude_deg\": origin.longitude,\n",
" \"source_longitude_uncertainty_km\": origin.longitude_errors[\"uncertainty\"],\n",
" \"source_depth_km\": origin.depth / 1e3,\n",
" \"source_depth_uncertainty_km\": origin.depth_errors[\"uncertainty\"] / 1e3 if origin.depth_errors[\"uncertainty\"] is not None else None,\n",
" }\n",
"\n",
" if mag is not None:\n",
" event_params[\"source_magnitude\"] = mag.mag\n",
" event_params[\"source_magnitude_uncertainty\"] = mag.mag_errors[\"uncertainty\"]\n",
" event_params[\"source_magnitude_type\"] = mag.magnitude_type\n",
" event_params[\"source_magnitude_author\"] = mag.creation_info.agency_id if mag.creation_info is not None else None\n",
" \n",
" return event_params\n",
"\n",
"\n",
"def get_trace_params(pick):\n",
" net = pick.waveform_id.network_code\n",
" sta = pick.waveform_id.station_code\n",
"\n",
" trace_params = {\n",
" \"station_network_code\": net,\n",
" \"station_code\": sta,\n",
" \"trace_channel\": pick.waveform_id.channel_code,\n",
" \"station_location_code\": pick.waveform_id.location_code,\n",
" \"time\": pick.time\n",
" }\n",
"\n",
" return trace_params\n",
"\n",
"\n",
"def get_trace_path(input_path, trace_params):\n",
"\n",
" year = trace_params[\"time\"].year\n",
" day_of_year = pd.Timestamp(str(trace_params[\"time\"])).day_of_year\n",
" net = trace_params[\"station_network_code\"]\n",
" station = trace_params[\"station_code\"]\n",
" tr_channel = trace_params[\"trace_channel\"]\n",
"\n",
" path = f\"{input_path}/{year}/{net}/{station}/{tr_channel}.D/{net}.{station}..{tr_channel}.D.{year}.{day_of_year}\"\n",
" return path"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "8415f6c1-0dfc-41e2-a06e-2e9bc94f0d4c",
"metadata": {},
"outputs": [],
"source": [
"def split_events(events, input_path):\n",
"\n",
" print(\"Splitting available events into train, dev and test sets ...\")\n",
" events_stats = pd.DataFrame()\n",
" events_stats.index.name = \"event\"\n",
" missing_mseeds = []\n",
"\n",
" for i, event in enumerate(events):\n",
" #check if mseed exists\n",
" actual_picks = 0\n",
" for pick in event.picks:\n",
" trace_params = get_trace_params(pick)\n",
" trace_path = get_trace_path(input_path, trace_params)\n",
" if os.path.isfile(trace_path):\n",
" actual_picks += 1\n",
" else: \n",
" missing_mseeds.append(trace_path.split('/'))\n",
" \n",
"\n",
" events_stats.loc[i, \"pick_count\"] = len(event.picks)\n",
" events_stats.loc[i, \"available_picks\"] = actual_picks\n",
" if len(event.picks):\n",
" events_stats.loc[i, \"first_peak_time\"] = trace_params[\"time\"]\n",
"\n",
" events_stats['pick_count_cumsum'] = events_stats.pick_count.cumsum()\n",
"\n",
" train_th = 0.7 * events_stats.pick_count_cumsum.values[-1]\n",
" dev_th = 0.85 * events_stats.pick_count_cumsum.values[-1]\n",
"\n",
" events_stats['split'] = 'test'\n",
" for i, event in events_stats.iterrows():\n",
" if event['pick_count_cumsum'] < train_th:\n",
" events_stats.loc[i, 'split'] = 'train'\n",
" elif event['pick_count_cumsum'] < dev_th:\n",
" events_stats.loc[i, 'split'] = 'dev'\n",
" else:\n",
" break\n",
"\n",
" missing_mseeds = pd.DataFrame(np.array(missing_mseeds)[:, -5:], columns=['y', 'n','s','tr','f'])\n",
" missing_mseeds['last_dot'] = missing_mseeds['f'].apply(lambda x: x.rindex('.'))\n",
"\n",
" for i, row in missing_mseeds.iterrows(): \n",
" missing_mseeds.loc[i, 'd'] = int(row['f'][row['last_dot']+1:])\n",
"\n",
"\n",
" return events_stats, missing_mseeds"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "96b8945a-06d6-498c-81d9-ba76788fdf37",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Splitting available events into train, dev and test sets ...\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/net/ascratch/people/plgkmilian/slurm_jobdir/5092284/tmp/ipykernel_248521/649615512.py:23: FutureWarning: Setting an item of incompatible dtype is deprecated and will raise in a future error of pandas. Value '2018-09-24T14:20:07.521000Z' has dtype incompatible with float64, please explicitly cast to a compatible dtype first.\n",
" events_stats.loc[i, \"first_peak_time\"] = trace_params[\"time\"]\n"
]
},
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>pick_count</th>\n",
" <th>available_picks</th>\n",
" <th>first_peak_time</th>\n",
" <th>pick_count_cumsum</th>\n",
" <th>split</th>\n",
" </tr>\n",
" <tr>\n",
" <th>event</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>NaN</td>\n",
" <td>0.0</td>\n",
" <td>train</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>10.0</td>\n",
" <td>8.0</td>\n",
" <td>2018-09-24T14:20:07.521000Z</td>\n",
" <td>10.0</td>\n",
" <td>train</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>10.0</td>\n",
" <td>10.0</td>\n",
" <td>2018-10-04T21:44:08.474000Z</td>\n",
" <td>20.0</td>\n",
" <td>train</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>12.0</td>\n",
" <td>10.0</td>\n",
" <td>2018-10-05T23:25:45.835000Z</td>\n",
" <td>32.0</td>\n",
" <td>train</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>10.0</td>\n",
" <td>10.0</td>\n",
" <td>2018-10-07T22:02:11.773000Z</td>\n",
" <td>42.0</td>\n",
" <td>train</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" pick_count available_picks first_peak_time \\\n",
"event \n",
"0 0.0 0.0 NaN \n",
"1 10.0 8.0 2018-09-24T14:20:07.521000Z \n",
"2 10.0 10.0 2018-10-04T21:44:08.474000Z \n",
"3 12.0 10.0 2018-10-05T23:25:45.835000Z \n",
"4 10.0 10.0 2018-10-07T22:02:11.773000Z \n",
"\n",
" pick_count_cumsum split \n",
"event \n",
"0 0.0 train \n",
"1 10.0 train \n",
"2 20.0 train \n",
"3 32.0 train \n",
"4 42.0 train "
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"events_stats, missing_mseeds = split_events(events, input_path)\n",
"events_stats.head()"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "4f2e3d49-03da-4086-8d42-a77c2aa29c5f",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>y</th>\n",
" <th>n</th>\n",
" <th>s</th>\n",
" <th>tr</th>\n",
" <th>f</th>\n",
" <th>last_dot</th>\n",
" <th>d</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>2018</td>\n",
" <td>PL</td>\n",
" <td>BOG5</td>\n",
" <td>EHN.D</td>\n",
" <td>PL.BOG5..EHN.D.2018.267</td>\n",
" <td>19</td>\n",
" <td>267.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2018</td>\n",
" <td>PL</td>\n",
" <td>BOG5</td>\n",
" <td>EHZ.D</td>\n",
" <td>PL.BOG5..EHZ.D.2018.267</td>\n",
" <td>19</td>\n",
" <td>267.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>2018</td>\n",
" <td>PL</td>\n",
" <td>BOG5</td>\n",
" <td>EHE.D</td>\n",
" <td>PL.BOG5..EHE.D.2018.278</td>\n",
" <td>19</td>\n",
" <td>278.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>2018</td>\n",
" <td>PL</td>\n",
" <td>BOG5</td>\n",
" <td>EHZ.D</td>\n",
" <td>PL.BOG5..EHZ.D.2018.278</td>\n",
" <td>19</td>\n",
" <td>278.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>2018</td>\n",
" <td>PL</td>\n",
" <td>BOG5</td>\n",
" <td>EHN.D</td>\n",
" <td>PL.BOG5..EHN.D.2018.281</td>\n",
" <td>19</td>\n",
" <td>281.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" y n s tr f last_dot d\n",
"0 2018 PL BOG5 EHN.D PL.BOG5..EHN.D.2018.267 19 267.0\n",
"1 2018 PL BOG5 EHZ.D PL.BOG5..EHZ.D.2018.267 19 267.0\n",
"2 2018 PL BOG5 EHE.D PL.BOG5..EHE.D.2018.278 19 278.0\n",
"3 2018 PL BOG5 EHZ.D PL.BOG5..EHZ.D.2018.278 19 278.0\n",
"4 2018 PL BOG5 EHN.D PL.BOG5..EHN.D.2018.281 19 281.0"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"missing_mseeds.head()"
]
},
{
"cell_type": "markdown",
"id": "fadeaa9e-b7d7-48c7-a09c-872a545f000f",
"metadata": {},
"source": [
"#### Check missing files"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "ffd246b8-118b-406a-bb87-4cd504970711",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"<Axes: title={'center': 'Missing mseeds grouped by year and station'}, xlabel='y,s'>"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 2000x400 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"missing_mseeds.groupby(['y','s']).size().plot(kind='bar', figsize=(20,4), title='Missing mseeds grouped by year and station')"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "24ee2524-6d1a-41a2-bc29-bb64905e8201",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th></th>\n",
" <th>min</th>\n",
" <th>max</th>\n",
" </tr>\n",
" <tr>\n",
" <th>y</th>\n",
" <th>s</th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>2018</th>\n",
" <th>BOG5</th>\n",
" <td>267.0</td>\n",
" <td>281.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th rowspan=\"4\" valign=\"top\">2019</th>\n",
" <th>ALBE</th>\n",
" <td>2.0</td>\n",
" <td>99.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>BARK</th>\n",
" <td>11.0</td>\n",
" <td>99.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>CYCO</th>\n",
" <td>2.0</td>\n",
" <td>99.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>DRAT</th>\n",
" <td>2.0</td>\n",
" <td>99.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th rowspan=\"5\" valign=\"top\">2023</th>\n",
" <th>OSTR</th>\n",
" <td>10.0</td>\n",
" <td>149.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>PIAS</th>\n",
" <td>12.0</td>\n",
" <td>124.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>PUCH</th>\n",
" <td>10.0</td>\n",
" <td>149.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>ROGO</th>\n",
" <td>12.0</td>\n",
" <td>149.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>WESO</th>\n",
" <td>10.0</td>\n",
" <td>149.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>62 rows ×
"</div>"
],
"text/plain": [
" min max\n",
"y s \n",
"2018 BOG5 267.0 281.0\n",
"2019 ALBE 2.0 99.0\n",
" BARK 11.0 99.0\n",
" CYCO 2.0 99.0\n",
" DRAT 2.0 99.0\n",
"... ... ...\n",
"2023 OSTR 10.0 149.0\n",
" PIAS 12.0 124.0\n",
" PUCH 10.0 149.0\n",
" ROGO 12.0 149.0\n",
" WESO 10.0 149.0\n",
"\n",
"[62 rows x 2 columns]"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"missing_mseeds.groupby(['y', 's'])['d'].agg(['min', 'max'])"
]
},
{
"cell_type": "code",
"execution_count": 106,
"id": "211c37be-e5eb-40ed-bbe8-0d7a5e92ae77",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"s\n",
"ALBE Axes(0.125,0.11;0.775x0.77)\n",
"BARK Axes(0.125,0.11;0.775x0.77)\n",
"CYCO Axes(0.125,0.11;0.775x0.77)\n",
"DRAT Axes(0.125,0.11;0.775x0.77)\n",
"GARB Axes(0.125,0.11;0.775x0.77)\n",
"KANI Axes(0.125,0.11;0.775x0.77)\n",
"KOPI Axes(0.125,0.11;0.775x0.77)\n",
"OSTR Axes(0.125,0.11;0.775x0.77)\n",
"PIAS Axes(0.125,0.11;0.775x0.77)\n",
"PUCH Axes(0.125,0.11;0.775x0.77)\n",
"ROGO Axes(0.125,0.11;0.775x0.77)\n",
"WESO Axes(0.125,0.11;0.775x0.77)\n",
"Name: d, dtype: object"
]
},
"execution_count": 106,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"missing_mseeds[missing_mseeds.y=='2019'].groupby(['s'])['d'].plot(kind='hist', legend=True)"
]
},
{
"cell_type": "code",
"execution_count": 64,
"id": "1ead7261-da65-4832-af20-f841a798febc",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"y\n",
"2018 6\n",
"2019 2540\n",
"2020 4486\n",
"2021 6507\n",
"2022 6111\n",
"2023 1379\n",
"dtype: int64"
]
},
"execution_count": 64,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"missing_mseeds.groupby('y').size()"
]
},
{
"cell_type": "code",
"execution_count": 17,
"id": "327f21de-64bc-49b1-849b-4d2d79b505ba",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(2099, 3)"
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"events_stats.shape"
]
},
{
"cell_type": "code",
"execution_count": 18,
"id": "a7407b0a-2efc-4c82-bf6a-8509dbdbc07c",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"<Axes: xlabel='event'>"
]
},
"execution_count": 18,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"events_stats.pick_count_cumsum.plot()"
]
},
{
"cell_type": "markdown",
"id": "12dbaa70-a178-4867-a710-0d8147ce4ecb",
"metadata": {},
"source": [
"### Transform mseeds to Seisbench format"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "80fc0198-6a1a-48e1-ada9-4faa048c6e69",
"metadata": {},
"outputs": [],
"source": [
"def find_trace(pick_time, traces): \n",
" for tr in traces: \n",
" if pick_time>tr.stats.endtime: \n",
" continue\n",
" if pick_time>=tr.stats.starttime: \n",
" # print(pick_time, \" - selected trace: \", tr)\n",
" return tr\n",
"\n",
" print(pick_time, \" no matching trace \")\n",
" return None\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "60ee1d41-d3db-4661-ade7-882bd2371f62",
"metadata": {},
"outputs": [],
"source": [
"def load_trace(input_path, trace_params):\n",
" trace_path = get_trace_path(input_path, trace_params)\n",
" trace, stream = None, None\n",
"\n",
" if not os.path.isfile(trace_path):\n",
" print(trace_path + \" not found\")\n",
" else:\n",
" stream = obspy.read(trace_path)\n",
" if len(stream.traces) > 1:\n",
" trace = find_trace(trace_params[\"time\"], stream.traces)\n",
" elif len(stream.traces) == 0:\n",
" print(\"no data in:\", trace_path)\n",
" else:\n",
" trace = stream.traces[0]\n",
"\n",
" return trace, stream\n",
"\n",
"\n",
"def load_stream(input_path, trace_params, time_before=60, time_after=60):\n",
" trace_path = get_trace_path(input_path, trace_params)\n",
" sampling_rate, stream = None, None\n",
" pick_time = trace_params[\"time\"]\n",
"\n",
" if not os.path.isfile(trace_path):\n",
" print(trace_path + \" not found\")\n",
" else:\n",
" stream = obspy.read(trace_path)\n",
" stream = stream.slice(pick_time - time_before, pick_time + time_after)\n",
" if len(stream.traces) == 0:\n",
" print(f\"no data in: {trace_path}\")\n",
" else:\n",
" sampling_rate = stream.traces[0].stats.sampling_rate\n",
"\n",
" return sampling_rate, stream"
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "7426f90a-4779-4c87-b445-4c41635a04f9",
"metadata": {},
"outputs": [],
"source": [
"metadata_path = output_path + \"/metadata.csv\"\n",
"waveforms_path = output_path + \"/waveforms.hdf5\"\n",
"train = 0.7\n",
"dev = 0.15\n",
"test = 0.15"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "cc393ac1-791e-414a-892f-e8cf0d8e2a12",
"metadata": {},
"outputs": [],
"source": [
"with sbd.WaveformDataWriter(metadata_path, waveforms_path) as writer:\n",
" writer.data_format = {\n",
" \"dimension_order\": \"CW\",\n",
" \"component_order\": \"ZNE\",\n",
" }\n",
" for i, event in enumerate(events):\n",
" logger.debug(f\"Converting {i} event\")\n",
" event_params = get_event_params(event)\n",
" event_params[\"split\"] = events_stats.loc[i, \"split\"]\n",
" # b = False\n",
"\n",
" for pick in event.picks:\n",
" trace_params = get_trace_params(pick)\n",
" sampling_rate, stream = load_stream(input_path, trace_params)\n",
" if stream is None:\n",
" continue\n",
"\n",
" actual_t_start, data, _ = sbu.stream_to_array(\n",
" stream,\n",
" component_order=writer.data_format[\"component_order\"],\n",
" )\n",
"\n",
" trace_params[\"trace_sampling_rate_hz\"] = sampling_rate\n",
" trace_params[\"trace_start_time\"] = str(actual_t_start)\n",
"\n",
" pick_time = obspy.core.utcdatetime.UTCDateTime(trace_params[\"time\"])\n",
" pick_idx = (pick_time - actual_t_start) * sampling_rate\n",
"\n",
" trace_params[f\"trace_{pick.phase_hint}_arrival_sample\"] = int(pick_idx)\n",
"\n",
" writer.add_trace({**event_params, **trace_params}, data)"
]
},
{
"cell_type": "markdown",
"id": "5cf46368-2e92-4aea-8fe8-298f3200f509",
"metadata": {},
"source": [
"### Load created dataset"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "bcbefdd8-91b0-461b-8677-5b10325822d0",
"metadata": {},
"outputs": [],
"source": [
"data = sbd.WaveformDataset(output_path, sampling_rate=100)"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "77f8060d-0703-41ce-ade8-c738e7a8e540",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"<seisbench.data.base.WaveformDataset at 0x14b58e696850>"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data"
]
},
{
"cell_type": "markdown",
"id": "ebc4f1ea-5e33-458d-82eb-ab6e5982ef63",
"metadata": {},
"source": [
"#### Check train/dev/test proportions"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "98f2ea18-18d8-4d7c-8e09-8c242842bda4",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"All samples: 6743\n",
"Training examples: 4720 70.0%\n",
"Development examples: 1009 15.0%\n",
"Test examples: 1014 15.0 %\n"
]
}
],
"source": [
"all_samples = len(data.train()) + len(data.dev()) + len(data.test())\n",
"print(\"All samples: \", all_samples)\n",
"print(f\"Training examples: {len(data.train())} {len(data.train())/all_samples * 100:.1f}%\" )\n",
"print(f\"Development examples: {len(data.dev())} {len(data.dev())/all_samples * 100:.1f}%\")\n",
"print(f\"Test examples: {len(data.test())} {len(data.test())/all_samples * 100:.1f} %\")"
]
},
{
"cell_type": "markdown",
"id": "5ffd0f88-5a5c-4f21-8688-b34d8540ad30",
"metadata": {},
"source": [
"#### Plot converted sample"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "c3af6da7-864f-490b-b260-733e49bd6d12",
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 1500x500 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"fig = plt.figure(figsize=(15, 5))\n",
"ax = fig.add_subplot(111)\n",
"\n",
"idx = 0\n",
"ax.plot(data.get_waveforms(idx).T)\n",
"ax.axvline(data.metadata[\"trace_Pg_arrival_sample\"].iloc[idx], color=\"green\", lw=1)\n",
"\n",
"plt.show()\n"
]
},
{
"cell_type": "code",
"execution_count": 18,
"id": "12d829c7-1478-4fc4-9b8f-565d4fdae824",
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 1500x500 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"fig = plt.figure(figsize=(15, 5))\n",
"ax = fig.add_subplot(111)\n",
"idx = 1\n",
"ax.plot(data.get_waveforms(idx).T)\n",
"# ax.axvline(data.metadata[\"trace_Pg_arrival_sample\"].iloc[idx], color=\"green\", lw=1)\n",
"ax.axvline(data.metadata[\"trace_Sg_arrival_sample\"].iloc[idx], color=\"black\", lw=1)\n",
"plt.show()"
]
},
{
"cell_type": "code",
"execution_count": 19,
"id": "d3534d4e-13a4-4780-8f7d-7490ae3608c6",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>trace_Pg_arrival_sample</th>\n",
" <th>trace_Sg_arrival_sample</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>5999.0</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>NaN</td>\n",
" <td>5999.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>NaN</td>\n",
" <td>6000.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>5999.0</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>6000.0</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6738</th>\n",
" <td>NaN</td>\n",
" <td>5999.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6739</th>\n",
" <td>5999.0</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6740</th>\n",
" <td>6000.0</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6741</th>\n",
" <td>NaN</td>\n",
" <td>5999.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6742</th>\n",
" <td>5999.0</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>6743 rows ×
"</div>"
],
"text/plain": [
" trace_Pg_arrival_sample trace_Sg_arrival_sample\n",
"0 5999.0 NaN\n",
"1 NaN 5999.0\n",
"2 NaN 6000.0\n",
"3 5999.0 NaN\n",
"4 6000.0 NaN\n",
"... ... ...\n",
"6738 NaN 5999.0\n",
"6739 5999.0 NaN\n",
"6740 6000.0 NaN\n",
"6741 NaN 5999.0\n",
"6742 5999.0 NaN\n",
"\n",
"[6743 rows x 2 columns]"
]
},
"execution_count": 19,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data.metadata[[\"trace_Pg_arrival_sample\", \"trace_Sg_arrival_sample\"]]"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "5d023f5f-120e-46ea-bfed-ead098fb247f",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
2023-10-12 14:27:53 +02:00
"version": "3.10.6"
2023-09-26 10:50:46 +02:00
}
},
"nbformat": 4,
"nbformat_minor": 5
}
